Abstract：[Objective] As pollutant emission is an important technical index of gas turbines, pollutant emission prediction has become one of the active research topics. However, the irregular strong turbulent combustion process in the combustion chamber of natural gas turbines causes chaotic pollutant generation, and the characteristics of low-emission combustion are extremely complex. The influence law of various geometric factors on pollutant generation characteristics is not clear. Moreover, the common pollutant prediction methods have certain limitations. For example, the numerical simulation method needs to be combined with a complex dynamic mechanism, resulting in a long calculation time. Therefore, this paper proposes to apply a neural network to the prediction of gas turbine pollutant emissions and develop a new method for the rapid and accurate prediction of pollutant emissions. [Methods] Computational fluid dynamics-based numerical simulation was used to study the influence of typical structural factors, such as the number of first-stage swirling flow, the number of second-stage swirling flow, and the fractional area ratio, on pollutant generation in the gas turbine combustion chamber, and to elucidate the variation trends of pollutant generation for different structures. The data were divided into a training set and a test set. Four structural parameters, namely the first-level swirl number, the second-level swirl number, the graded area ratio, and the graded axial distance of the combustion chamber head, were defined as input variables; the NOx and CO emissions at the combustion chamber outlet were defined as output variables for neural network training calculation; and then the radical basis function (RBF) neural network prediction model was established. The model structure was determined as 4-22-2. [Results] The results showed that for the studied coaxial graded combustor, the increase in the swirl number will lead to the increased and backward movement of the vortex core in the return zone, and the increase of the graded area ratio will lead to an increase in the equivalent ratio in the center of the return zone, which will increase the intensity of chemical reactions in the combustor, the maximum temperature, and the NOx emission. The CO emission in the combustion chamber was not sensitive to the typical structural parameters of the combustion chamber head, and the CO emission at the combustion chamber outlet exhibited little change with the variation of different structural parameters, such as swirl number, fractional area ratio, and fractional axial distance. The established combustion chamber emission RBF neural network prediction model could accurately and rapidly predict the combustion chamber outlet emission under different structural parameters. The maximum prediction error of NOx emission was 12.28%, and the average error was 4.58%; the maximum prediction error of CO emission was 2.75%, and the average error was 0.97%. [Conclusion] In this study, the characteristics of gas turbine pollutant generation are analyzed via numerical simulation, and the results prove that the neural network prediction model can effectively predict the characteristics of gas turbine pollution emission with good feasibility and high accuracy.
孙继昊, 宋颖, 石云姣, 赵宁波, 郑洪涛. 天然气同轴分级燃烧室污染物生成及预测[J]. 清华大学学报（自然科学版）, 2023, 63(4): 649-659.
SUN Jihao, SONG Ying, SHI Yunjiao, ZHAO Ningbo, ZHENG Hongtao. Prediction of the pollutant generation of a natural gas-powered coaxial staged combustor. Journal of Tsinghua University(Science and Technology), 2023, 63(4): 649-659.
[1] 王会祥,王秋明.燃气轮机电厂氮氧化物排放浓度标准比较与实测验证[J].中外能源, 2018, 23(4):86-90. WANG H X, WANG Q M. Comparative analysis of NOx emission standards for gas turbine power plant and the test verification[J]. Sino-Global Energy, 2018, 23(4):86-90.(in Chinese) [2] 中华人民共和国国家质量监督检验检疫总局,中国国家标准化管理委员会.火电厂大气污染物排放标准:GB 13223-2011[S].北京:中国环境科学出版社, 2012. General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China National Standardization Administration. Emission standard of air pollutants for thermal power plants:GB 13223-2011[S]. Beijing:China Environmental Press, 2012.(in Chinese) [3] 李苏辉,张归华,吴玉新.面向未来燃气轮机的先进燃烧技术综述[J].清华大学学报(自然科学版), 2021, 61(12):1423-1437. LI S H, ZHANG G H, WU Y X. Advanced combustion technologies for future gas turbines[J]. Journal of Tsinghua University (Science and Technology), 2021, 61(12):1423-1437.(in Chinese) [4] 刘威,王成军,郑顺,等.旋流器结构参数对燃烧室燃烧性能影响的数值分析[J].燃气涡轮试验与研究, 2020, 33(1):19-26. LIU W, WANG C J, ZHENG S, et al. Numerical analysis of influence of Swirler structure parameters on combustion performance of central-staged combustor[J]. Gas Turbine Experiment and Research, 2020, 33(1):19-26.(in Chinese) [5] 袁怡祥,林宇震,刘高恩.三旋流器头部燃烧室拓宽燃烧稳定工作范围的研究[J].航空动力学报, 2004, 19(1):142-147. YUAN Y X, LIN Y Z, LIU G E. Combustor dome design with three swirlers for widening the operation stability range[J]. Journal of Aerospace Power, 2004, 19(1):142-147.(in Chinese) [6] 葛臣.结构参数对环管型燃烧室燃烧及NOx生成的影响[D].北京:华北电力大学, 2019. GE C. Influence of structural parameter on combustion and NOx formation in can-annular combustion chamber[D]. Beijing:North China Electric Power University, 2019.(in Chinese) [7] LEFEBVRE A H. Fuel effects on gas turbine combustion-liner temperature, pattern factor, and pollutant emissions[J]. AIAA Journal of Aircraft, 1982, 21(11):887-898. [8] RØKKE N A, HUSTAD J E, BERG S. Pollutant emissions from gas fired turbine engines in offshore practice:Measurements and scaling[C]//ASME 1993 International Gas Turbine and Aeroengine Congress and Exposition. Cincinnati, USA:ASME, 1993. [9] 金戈,顾铭企,李孝堂.燃气轮机干式低排放燃烧室NOx排放评估[J].燃气轮机技术, 2007, 20(4):50-53, 64. JIN G, GU M Q, LI X T. The evaluation of NOx emission performance of gas turbine DLE combustor[J]. Gas Turbine Technology, 2007, 20(4):50-53, 64.(in Chinese) [10] 谢刚,祁海鹰,李宇红,等. R0110重型燃气轮机燃烧室污染排放性能研究[J].中国电机工程学报, 2010, 30(20):51-57. XIE G, QI H Y, LI Y H, et al. Emission performance of the dry low NOx combustors for R0110 heavy-duty gas turbine[J]. Proceedings of the CSEE, 2010, 30(20):51-57.(in Chinese) [11] 赵刚,朱华昕,李苏辉,等.基于数据和神经网络的燃气轮机NOx排放预测与优化[J].动力工程学报, 2021, 41(1):22-27. ZHAO G, ZHU H X, LI S H, et al. NOx emission prediction and optimization for gas turbines based on data and neural network[J]. Journal of Chinese Society of Power Engineering, 2021, 41(1):22-27.(in Chinese) [12] AZZAM M, AWAD M, ZEAITER J. Application of evolutionary neural networks and support vector machines to model NOx emissions from gas turbines[J]. Journal of Environmental Chemical Engineering, 2018, 6(1):1044-1052. [13] MONGIA H C. Combining Lefebvre's correlations with combustor CFD[J]. AIAA, 2004, 2004-3544. [14] 陈晓丽,祁海鹰,谢刚,等. DLN燃烧室污染排放估算方法的分析[J].热能动力工程, 2010, 25(6):599-604, 683. CHEN X L, QI H Y, XIE G, et al. Analysis of pollution emission estimation method of DLN combustion chamber[J]. Journal of Thermal Energy and Power Engineering, 2010, 25(6):599-604, 683.(in Chinese) [15] SHEHATA M. Emissions and wall temperatures for lean prevaporized premixed gas turbine combustor[J]. Fuel, 2009, 88:446-455. [16] 林清华,张哲巅,肖云汉.合成气燃烧室NOx排放估算方法分析[J].燃气轮机技术, 2013, 26(1):9-14, 26. LIN Q H, ZHANG Z D, XIAO Y H. Analysis of the methods for estimating NOx emissions from syngas combustor[J]. Gas Turbine Technology, 2013, 26(1):9-14, 26.(in Chinese) [17] 郑洪涛,穆勇,李智明,等.湍流燃烧模型在燃气轮机燃烧室模拟中的运用与对比[J].热能动力工程, 2010, 25(1):12-16. ZHENG H T, MU Y, LI M Z, et al. Application and contrast of turbulent-flow combustion models for simulating a gas turbine combustor[J]. Journal of Engineering for Thermal Energy and Power, 2010, 25(1):12-16.(in Chinese) [18] MAYR B, PRIELER R, DEMUTH M, et al. The usability and limits of the steady flamelet approach in oxy-fuel combustions[J]. Energy, 2015, 90:1478-1489. [19] WARNATZ J. NOx formation in high temperature processes[D]. Stuttgart:University of Stuttgart, 2001. [20] BAULCH D L, COBOS C J, COX R A, et al. Evaluated kinetic data for combustion modelling[J]. Journal of Physical and Chemical Reference Data, 1992, 21(3):411-734. [21] BULAT G, JONESA W P, MARQUIS A J. NO and CO formation in an industrial gas-turbine combustion chamber using LES with the Eulerian sub-grid PDF method[J]. Combustion and Flame, 2014, 161(7):1804-1825. [22] 于静,金秀章,刘岳.基于结构改进RBF神经网络的NOx预测模型比较[J/OL].(2021-06-05)[2022-10-17]. https://doi.org/10.14107/j.cnki.kzgc.20210150. YU J, JIN X Z, LIU Y. Comparison of NOx prediction models based on improved RBF neural network[J/OL].(2021-06-05)[2022-10-17]. https://doi.org/10.14107/j.cnki.kzgc.20210150.(in Chinese) [23] 周昊,朱洪波,岑可法.基于人工神经网络和遗传算法的火电厂锅炉实时燃烧优化系统[J].动力工程, 2003, 23(5):2665-2669. ZHOU H, ZHU H B, CEN K F. An on-line boiler operating optimization system based on the neural network and the genetic algorithms[J]. Power Engineering, 2003, 23(5):2665-2669.(in Chinese) [24] 王志凯,陈盛,范玮.神经网络宽度对燃烧室排放预测的影响[J/OL].(2022-01-20)[2022-05-26]. http://kns.cnki.net/kcms/detail/11.1929.V.20220119.1003.016.html. WANG Z K, CHEN S, FAN W. Effect of neural network width on combustor emission prediction[J/OL].(2022-01-20)[2022-05-26]. http://kns.cnki.net/kcms/detail/11.1929.V.20220119.1003.016.html.(in Chinese)
2023, Vol. 63 
